Understanding Scenery Quality: A Visual Attention Measure and Its Computational Model

Yuen Peng Loh, Song Tong, Xuefeng Liang, Takatsune Kumada, Chee Seng Chan; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 289-297

Travel photos record tourists' experiences and attentions when visiting a place. We question if they embed any untapped indices, subconsciously created by the tourists, for measuring the scenery quality? By analyzing thousands of such photos and inspired by the psychological theory of "broaden-and-build", our study reveals a strong inclination of taking panoramic photos at high rating outdoor tourist spots. Thus, this preference can be a supplementary measure of indexing the scenery quality. However, the task of recognizing panoramic photos is nontrivial. In this paper, we propose a visual attention inspired computational model to address this issue, which mimics human perceptual and cognitive mechanisms by a focus model and a scale model. The experiments on a newly created dataset demonstrate a remarkable performance of our proposal, along with its effectiveness in measuring scenery quality also verified by 10 high rating outdoor spots and 2 lower rating ones from across the world.